Hey, marketers in the loop.

29% of CMOs surveyed by Salesforce's State of Marketing report said they are concerned about AI's inaccurate outputs. So, we decided to deep dive and provide a quick playbook on how to avoid AI hallucination.

We are also launching a new section in the newsletter to cover case studies from top brands. This week we are exploring how Hersheys used AI to boost their Halloween campaign. It seems we are all going to eat more Kit Kat later this month. 🎃🍫

As usual, email me if you have suggestions for improvement. I read and respond to all messages.

Onward.

In this issue:

• How to avoid AI hallucination?

• AI spices up Hershey’s Halloween campaign

• Lots of search opinions and updates

• And much more

Reading time: 8 minutes

MY FAVORITE FINDS

Industry News

Google's share of the search ad market could drop below 50% for the first time in a decade as AI search engines boom (Business Insider)

Marketers are not won over by new AI-powered search tools (Digiday)

Google is upgrading shopping research with the help of AI (Google)

New ProSearch feature allows Perplexity users to generate visual data charts (Testing Catalog)

5 trends seen at Advertising Week New York 2024, from AI buzz to signal loss woes (The Drum)

Zoom will let AI avatars talk to your team for you (The Verge)

X Updates Terms of Service to More Explicitly Cover AI Training Permissions (Social Media Today)

TikTok shifts to AI moderation, laying off hundreds, while Instagram blames human error for recent mishaps (Tech Edition)

Adobe Introduces Adobe Content Authenticity Web App to Champion Creator Protection and Attribution (Adobe)

Europe’s privacy patrol is spoiling Big Tech’s AI party (Politico)

Thought Leadership

Why marketers need to master capability assessment and tool procurement (Martech)

Will AI agents kill advertisements? Yes, yes, no, and yes (Jeremiah Owyang on Linkedin)

AI SEO: How to be visible in Google AI Overviews, chatbots, LLMs (Search Engine Land)

Anthropic CEO goes full techno-optimist in 15,000-word paean to AI (TechCrunch)

If you got interested in the Anthropic's CEO manifesto, you must read this piece by Ina Fried (Axios AI+)

AI and marketing: What the recent stats show (MarTech)

2024 Generative AI marketing industry report (Social Media Examiner)

AI hype gives way to skepticism: Only 26% of consumers trust organizations to use AI responsibly (Qualtrics)

A new tech-driven era of impactful marketing and sales (McKinsey)

An unconstrained future: How generative AI could reshape B2B sales (McKinsey)

DEEP DIVE

Minimizing AI Hallucinations: A Marketer's Playbook

The big picture: Although AI tools are improving, they can still "hallucinate" - generate plausible yet incorrect information - which poses a significant challenge.

Why it matters: Marketers need strategies to harness AI's power while ensuring accuracy and reliability in their outputs. Otherwise, incorrect information could confuse customers, damage brand credibility, and negatively impact the customer experience.

The challenge: AI excels at mimicking human-like language but lacks inherent understanding of truth. This can lead to fabricated details or misleading claims presented as facts, like a lawyer filing paperwork with made-up case law or the Air Canada support chatbot hallucinating a policy.

• AI predicts likely word sequences, not factual accuracy.

• Human judgment and critical thinking remain crucial.

5 strategies to minimize AI hallucinations:

1. Know your AI and its limits

• Understand the capabilities, strengths, and limitations of each tool (i.e.: some tools can access the web, others can’t) and match the AI to the task. Don’t use foundation models for tasks they aren’t trained to do.

• Stay updated on model versions and features. When and in which domains a model was trained can impact outputs, leading to outdated, incorrect, or insufficient data if your prompt requires recent knowledge.

• Test AI tools with sample tasks before full implementation, and consider piloting internal workflows (not customer-facing) first. As an example, start with generating drafts for internal communications before creating campaign ads.

2. Prioritize data quality and relevance

• Anchoring your AI in verified information reduces hallucinations and produces more reliable outputs. For tools that can access the web, you can instruct the model to source information from trusted online sources like eMarketer.

• Most tools allow you to train them with your data (i.e.: ChatGPT offers custom GPTs). Feed AI comprehensive, up-to-date high-quality datasets that reflect real-world and task-specific scenarios. Regularly update and expand this information to maintain relevance.

• Garbage in, garbage out. Ensure data accuracy by cleaning and validating it before input. When possible, combine internal and external sources like CRM, survey, and industry reports for a well-rounded dataset.

3. Master the art of prompt engineering

• Be specific: When formulating your prompt, be as clear and specific as possible about what you want the AI to do. Instead of vague requests, provide detailed instructions that guide it towards the desired output.

• Add context: Giving the AI model proper context is crucial for generating accurate responses. Provide background information or specific data sources to help it understand the scope and focus of your query.

• Define output format: Defining the desired output format can help the AI structure its response more effectively. This can include specifying the number of words, points, paragraphs, formatting elements or simply “be concise”.

• Use negative prompting: Tell the AI what you don't want to see in its response to avoid unwanted content or irrelevant information. i.e.: Don’t search the web and only use data you were trained on, or even “don’t make up anything”.

• Keep it simple: Use straightforward and simple language in your prompts to reduce the risk of misinterpretation. Avoid complex jargon or ambiguous terms that might confuse the AI.

• Limit options: When appropriate, restrict the AI's response options to reduce the scope for hallucinations. This can be particularly useful for specific queries or when you need a focused answer.

• Break it down: For complex queries, break the task into smaller steps. This helps guide most of the AI models through the process and reduces the likelihood of hallucinations.

• Data sources: Prompts asking for evidence compel the AI to generate responses grounded in data. Ask AI to double-check its results and provide references for human verification. If needed, ask it to look for the same information in other sources.

4. Trust, but verify all outputs

• Use AI outputs as drafts for human refinement. Have experts review AI-generated outputs. I.e.: After generating a product description using AI, have a product manager review it for accuracy.

• Fact-check using trusted sources and, if the case, cross-reference outputs from different tools. Provide feedback to correct AI mistakes for improvement.

• Implement a multi-step review process for critical content based on the above. To assess the need for extra eyes, consider the likelihood of an issue and its potential impact.

5.User education and expectations

• AI isn’t an infallible source of information. Be transparent about its limitations and safe usage.

• Establish training and clear guidelines within your organization. Remember, “repetition is the mother of learning,” so be creative to reinforce it over time.

• Continuously review workflows and internal practices for improvement. AI is advancing rapidly, so it’s important to keep up and adjust as needed.

The bottom line: While AI hallucinations pose a real challenge, understanding their nature and implementing these five strategies can minimize their occurrence.

What's next: As AI technology evolves, expect:

• More sophisticated fact-checking capabilities built into AI tools.

• Increased transparency about AI limitations and confidence levels.

• Growing emphasis on AI ethics and responsible use in marketing.

Be smart: Approach it as a powerful tool that requires careful handling, human oversight, and continuous learning. This will allow us to harness its full potential while ensuring accuracy, reliability, and ethical use.

PS: Interested in listening to a podcast-like summary of this article on NotebookLM? You got it.

CASE STUDY

Hershey’s AI-Powered Halloween Campaign

Challenges:

Halloween is a critical sales season for Hershey, and the brand wanted to optimize its media spending to maximize reach and ROI. Managing ad placements manually across numerous platforms proved time-consuming and lacked the agility to adapt in real-time.

Solution:

Hershey implemented AI to streamline its media buying process across platforms like Meta, YouTube, and The Trade Desk. AI helped automate ad placements and optimize budget allocations by analyzing real-time data to determine where ads performed best. By adjusting media spend dynamically, Hershey could ensure better visibility for its Halloween campaigns while maintaining efficiency.

Results:

• Increased efficiency in media buying, with faster adjustments based on campaign performance.

• Improved ROI due to smarter budget allocations across multiple platforms.

• Higher engagement and brand visibility during the critical Halloween period, driving stronger sales.

Key Takeaways:

Hershey’s use of AI for media buying illustrates the power of machine learning in enhancing traditional marketing strategies. Automating the process allowed for real-time optimizations that significantly improved performance, proving that AI can be a game-changer during peak sales seasons.

Click here for more details.

Did you like this email? Share this link with a friend for a virtual hug!